Now, using the formulae, we can calculate the values of Ea and Eb. These assumptions and the formula actually made sense as the expectations of girl being hotter that the other cannot be calculated independently and must involve the rating of both the girls being compared!
But, when we apply these formulae, one can get some absurd results. So, we can assume that the formulae in the movie were just given to understand the basic logic of comparing the expectations of a girl being hotter than the other. This is a cool tech related moment on-screen which is completely grounded in reality, somewhat of a rarity on screen.
Congratulations todayintech! You have completed some achievement on Steemit and have been rewarded with new badge s :. You got your First payout Award for the total payout received. Click on any badge to view your own Board of Honor on SteemitBoard. For more information about SteemitBoard, click here. If you no longer want to receive notifications, reply to this comment with the word STOP.
By upvoting this notification, you can help all Steemit users. Learn how here! Interesting read. I wonder how long it will be before they make a film about Ned and Dan from Steemit :. All posts. For example, if Girl A had won half her matches, Ra would be 0. Similarly, if Girl B has won only one of five matches, Rb would be 0. That made sense to me for the brief moment it was displayed in the movie, but actually playing with the equations yields non-useful results.
For example, assume Girl A has won 5 of 10 matches, and Ra is 0. Assume Girl B has won 2 of 8 matches, and Rb is 0.
In other words, it is twice as likely that Girl A will win as compared to Girl B winning. Instead the results are nonsensical. My guess is that one of the following issues is occurring: 1 My memory of the equations is incorrect. I searched for awhile for formal algorithms to perform ordering based on head-to-head contest results and came up empty. So the algorithm I use is based on my own best reasoning. Your recollection of the equation is fairly accurate.
Everyone starts off at a rating of , which I assume is the number of total girls that Mark has in the data base. Now suppose girl A and girl B battle it out in cyberspace, their fate decided by the click of testosterone fueled horny Harvard guy late on a Friday night with no gf. The guy chooses girl A. Ea and Eb are now both 1 assign to both Rb and Ra.
The question is, how do these values of Ea and Eb change. The second part of the equation is not shown on the Social Network. E is either Eb, or Ea, depending on which players new rating we are calculating. The losing players rating will decrease, while the winning players rating will stay the same assuming they both started out with exactly the same rating, both ratings will change if players start out with ratings that are at all different.
The highest rated girl is ranked the highest. The beauty of the game as set up in Facesmash is that you have the opportunity to have the game played a lot of times, and the ability to set up players girls faces at random. This would give an extremely accurate ranking of whose girls face is really considered hot by the community of horny college guys. The same for Rb. Thanks to Haseeb and Mariano for great comments.
I linked to the Wikipedia page for the Elo system in my update post , however I think Haseeb and Mariano explain the mechanics of the system better, anyway. The actual outcome W minus the expected outcome Ea. The United States Chess Federation maintains an absolute ratings floor of for all ratings. Thus, no member can have a rating below Inspired from Facemash, is there a desktop application that: 1 Scans the pictures in a folder 2 Shows two random pictures and asks me to choose which one I prefer 3 The picture I prefer will be the winner and gets a higher rating as in chess ratings , while the losing picture loses rating 4 Repeats steps 2 and 3 indefinitely till it decides the ratings the pictures are accurate 5 Sorts the images by their rating.
Hi guys! Great break-down of the algorithm, thanx! But in my application the total number of users from which I will pick two for the duel will increase during the time.
So I have two problems… I dont know how should I set the initial score of a new user and how to handle the fact, that at a time some user had already been to e. I guess the only answer to the second problem would be to pick the users for duel based on number of duels they have already been in, in order to set more appropriate score as fast as possible. Has anyone implemented this algorithm in php yet? Reid Barton Reid Barton In that case, I found a couple links. PHP: webscripts.
I recreated it aswell check it out. Luke Luke 3, 2 2 gold badges 20 20 silver badges 22 22 bronze badges. It says 'as seen in The Social Network' but it looks really different. In the movie it's with a thick, red header and a white background colour. How did you get so many people using your site?
Luke — user Link appears to be a Can you post the code somewhere else? Nour Wolf Nour Wolf 1, 23 23 silver badges 23 23 bronze badges.
Henrik P. Hessel Henrik P. Hessel Mike Mike 58 2 2 silver badges 10 10 bronze badges. The Overflow Blog. Podcast Explaining the semiconductor shortage, and how it might end.
Does ES6 make JavaScript frameworks obsolete?
0コメント